Analyzing Digital Image by Deep Learning for Melanoma Diagnosis

Image classification is an important task in many medical applications, in order to achieve an adequate diagnostic of different lesions. Melanoma is a frequent kind of skin cancer, which most of them can be detected by visual exploration. Heterogeneity and database size are the most important difficulties to overcome in order to obtain a good classification performance. In this work, a deep learning based method for accurate classification of wound regions is proposed. Raw images are fed into a Convolutional Neural Network (CNN) producing a probability of being a melanoma or a non-melanoma. Alexnet and GoogLeNet were used due to their well-known effectiveness. Moreover, data augmentation was used to increase the number of input images. Experiments show that the compared models can achieve high performance in terms of mean accuracy with very few data and without any preprocessing.